¹College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou,China
²Key Laboratory of Gansu Advanced Control for Industrial Processes,Lanzhou,China
³Manufacturing Engineering Technology Research Center of Gansu,Lanzhou,China
⁴College of Computer and Communication, Lanzhou University of Technology, Lanzhou ,China

---

Abstract—In this paper, a new face recognition method based on kernel discriminate local preserve projection(KDLPP) and Multi-feature fusion under smart environment is proposed . In order to solve the small sample size problem, combined with kernel theory and QR decomposition, a new face recognition algorithm named kernel discriminate local preserve projection is proposed based on discriminate local preserve projection algorithm. considered the external features are useful in face recognition, because hair is a highly variable feature of human face ,so we combined hair features and DCT features on the feature layer. The experiments on the AMI database indicate the proposed method can enhance the accuracy of the recognition system effectively.

Index Terms—Kernel Discriminate Local Preserve Projection(KDLPP), Hair Feature, Discrete Cosine Transform, Feature Fusion.

[PDF]

Cite: Di Wu, Jie Cao, Jinhua Wang, Wei Li, "Multi-feature Fusion Face Recognition Based on Kernel Discriminate Local Preserve Projection Algorithm under Smart Environment," Journal of Computers vol. 7, no. 10, pp. 2479-2487, 2012.